© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12733
    Prev
    Next
    INDEX
    Explanations

    mentions of the Internet of Things (IoT) and related applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     copas
    -0.31
    itária
    -0.30
    Erstellt
    -0.29
    beitung
    -0.28
    Trayectoria
    -0.27
     avanti
    -0.27
     Copy
    -0.26
     alternativas
    -0.26
     DVD
    -0.26
    COPY
    -0.26
    POSITIVE LOGITS
     IoT
    1.41
    IoT
    1.23
     IOT
    1.11
     smart
    1.08
     sensors
    1.04
    iot
    0.96
     sensor
    0.96
     Smart
    0.94
    IOT
    0.93
    smart
    0.89
    Activations Density 0.282%

    No Known Activations